alexandonian

whisper.cpp

Port of OpenAI's Whisper model in C/C++

OpenVoice

Instant voice cloning by MyShell.

DeepFaceLive

Real-time face swap for PC streaming or video calls

open-webui

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

pykan

Kolmogorov Arnold Networks

phidata

Build AI Assistants with memory, knowledge and tools.

storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

torchtune

A Native-PyTorch Library for LLM Fine-tuning

cohere-toolkit

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

maestro

A framework for Claude Opus to intelligently orchestrate subagents.

mistral.rs

Blazingly fast LLM inference.

torchtitan

A native PyTorch Library for large model training

nanotron

Minimalistic large language model 3D-parallelism training

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

visual_anagrams

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

kerkour.com

(Ab)using technology for fun & profit. Programming, Hacking & Entrepreneurship @ https://kerkour.com

ring-flash-attention

Ring attention implementation with flash attention

PLLaVA

Official repository for the paper PLLaVA

MathPile

Generative AI for Math: MathPile

paperetl

📄 ⚙️ ETL processes for medical and scientific papers

arena-hard

Arena-Hard benchmark

ollama-grid-search

A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.

llamaduo

Mixture-of-depths

Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"

SoM-LLaVA

Empowering Multimodal LLMs with Set-of-Mark Prompting and Improved Visual Reasoning Ability.

Mixture-of-Depths

Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"

Neuroformer

Token-level-Direct-Preference-Optimization

Reference implementation for Token-level Direct Preference Optimization(TDPO)

llm-uncertainty

code repo for ICLR 2024 paper "Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs"

unified-model-editing

We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.